<<<<<<< HEAD ======= >>>>>>> f158664ada3587c008672ed01bb08c81b8c8224b
In [53]:
import pandas as pd
import numpy as np 
import matplotlib.pyplot as plt
# import seaborn as sns 
import datetime
from plotly.offline import download_plotlyjs, init_notebook_mode, plot, iplot
from plotly.graph_objs import Scatter, Figure, Layout
import plotly
import plotly.graph_objs as go
import plotly.express as px
init_notebook_mode(connected=False)
import io
import requests
import re

COVID-19 in Italy. Visuals

<<<<<<< HEAD

 

=======
(alternatively, see results with full code in Jupyter notebook here)
>>>>>>> f158664ada3587c008672ed01bb08c81b8c8224b

Data source: this GitHubi page

Authors and sources mentioned: Editore/Autore del dataset: Dipartimento della Protezione Civile. Categoria ISO 19115: Salute. Dati forniti dal Ministero della Salute.

Regional data files (Dati per Regione):
  • Struttura file giornaliero: dpc-covid19-ita-regioni-yyyymmdd.csv (dpc-covid19-ita-regioni-20200224.csv)
  • File complessivo: dpc-covid19-ita-regioni.csv
  • File ultimi dati (latest): dpc-covid19-ita-regioni-latest.csv
<<<<<<< HEAD

 

======= >>>>>>> f158664ada3587c008672ed01bb08c81b8c8224b <<<<<<< HEAD
======= >>>>>>> f158664ada3587c008672ed01bb08c81b8c8224b
In [63]:
URL='https://it.wikipedia.org/wiki/Regione_(Italia)'
res=requests.get(URL)
tables=pd.read_html(res.text)
dt = tables[13]
In [64]:
dt2 = dt[['Regione','Popolazione (ab.)']].copy()
dt2.columns = ['Region','Pop']

def dewhite(x):
    ''.join(re.findall('\d+', x))
    
dt2.Pop = dt2.Pop.apply(lambda x: ''.join(re.findall('\d+', x))).astype(int)
Current data as of the date:
In [65]:
s = requests.get("https://raw.githubusercontent.com/pcm-dpc/COVID-19/master/dati-regioni/dpc-covid19-ita-regioni.csv").content
dat = pd.read_csv(io.StringIO(s.decode('utf-8')))
print(dat.data.max())
<<<<<<< HEAD
======= 
2020-10-12T17:00:00
In [66]:
print('Showing all variable names in the original dataframe')
dat.columns

Showing all variable names in the original dataframe
Out[66]:
Index(['data', 'stato', 'codice_regione', 'denominazione_regione', 'lat',
       'long', 'ricoverati_con_sintomi', 'terapia_intensiva',
       'totale_ospedalizzati', 'isolamento_domiciliare', 'totale_positivi',
       'variazione_totale_positivi', 'nuovi_positivi', 'dimessi_guariti',
       'deceduti', 'casi_da_sospetto_diagnostico', 'casi_da_screening',
       'totale_casi', 'tamponi', 'casi_testati', 'note'],
      dtype='object')
>>>>>>> f158664ada3587c008672ed01bb08c81b8c8224b 
2020-10-12T17:00:00
<<<<<<< HEAD

 

What's in the original dataframe?

In [66]:
print('Showing all variable names')
dat.columns
=======





In [67]:



    


df = dat.drop(['stato','codice_regione'], axis=1)
df.columns = ['Date','Region','Lat','Long','HospWithSymptoms','IC','HospTotal','AtHome','CurrentlyPositive','VariationOfPositives','NewPositives','Recovered', 'Deaths','Diagnostico','Screening','TotalCases','NoOfTests','casi_testati','note']

df = pd.merge(df, dt2, left_on='Region', right_on='Region')

df['Date'] = pd.to_datetime(df['Date']).dt.date
df = df.set_index(df["Date"])
df.index = pd.to_datetime(df.index)

df['NewPositives'] = np.abs(df['NewPositives'])

print("Showing last 5 rows of the original dataframe")
dat.tail(5)
>>>>>>> f158664ada3587c008672ed01bb08c81b8c8224b



    















    





<<<<<<< HEAD

Showing all variable names in the original dataframe
=======

Showing last 5 rows of the original dataframe
>>>>>>> f158664ada3587c008672ed01bb08c81b8c8224b










<<<<<<< HEAD
    
Out[66]:








Index(['data', 'stato', 'codice_regione', 'denominazione_regione', 'lat',
       'long', 'ricoverati_con_sintomi', 'terapia_intensiva',
       'totale_ospedalizzati', 'isolamento_domiciliare', 'totale_positivi',
       'variazione_totale_positivi', 'nuovi_positivi', 'dimessi_guariti',
       'deceduti', 'casi_da_sospetto_diagnostico', 'casi_da_screening',
       'totale_casi', 'tamponi', 'casi_testati', 'note'],
      dtype='object')





















 


Rows for the last 5 days












In [81]:



    


df = dat.drop(['stato','codice_regione'], axis=1)
df.columns = ['Date','Region','Lat','Long','HospWithSymptoms','IC','HospTotal','AtHome','CurrentlyPositive','VariationOfPositives','NewPositives','Recovered', 'Deaths','Diagnostico','Screening','TotalCases','NoOfTests','casi_testati','note']

df = pd.merge(df, dt2, left_on='Region', right_on='Region')

df['Date'] = pd.to_datetime(df['Date']).dt.date
df = df.set_index(df["Date"])
df.index = pd.to_datetime(df.index)

df['NewPositives'] = np.abs(df['NewPositives'])

dat.tail(5)



    















    
Out[81]:

=======
    
Out[67]:

>>>>>>> f158664ada3587c008672ed01bb08c81b8c8224b










  
    

      
      data
      stato
      codice_regione
      denominazione_regione
      lat
      long
      ricoverati_con_sintomi
      terapia_intensiva
      totale_ospedalizzati
      isolamento_domiciliare
      ...
      variazione_totale_positivi
      nuovi_positivi
      dimessi_guariti
      deceduti
      casi_da_sospetto_diagnostico
      casi_da_screening
      totale_casi
      tamponi
      casi_testati
      note
    

  
  
    

      4867
      2020-10-12T17:00:00
      ITA
      19
      Sicilia
      38.115697
      13.362357
      404
      42
      446
      4236
      ...
      281
      298
      4571
      339
      6133.0
      3459.0
      9592
      552826
      397546.0
      NaN
    

    

      4868
      2020-10-12T17:00:00
      ITA
      9
      Toscana
      43.769231
      11.255889
      205
      40
      245
      6259
      ...
      362
      466
      10942
      1180
      14189.0
      4437.0
      18626
      848466
      570706.0
      NaN
    

    

      4869
      2020-10-12T17:00:00
      ITA
      10
      Umbria
      43.106758
      12.388247
      61
      9
      70
      1300
      ...
      134
      148
      2012
      90
      1844.0
      1628.0
      3472
      233252
      138736.0
      NaN
    

    

      4870
      2020-10-12T17:00:00
      ITA
      2
      Valle d'Aosta
      45.737503
      7.320149
      9
      3
      12
      213
      ...
      28
      32
      1125
      146
      1352.0
      144.0
      1496
      31492
      21680.0
      NaN
    

    

      4871
      2020-10-12T17:00:00
      ITA
      5
      Veneto
      45.434905
      12.338452
      244
      29
      273
      6016
      ...
      201
      328
      23323
      2219
      22250.0
      9581.0
      31831
      2069955
      808554.0
      NaN
    

  



5 rows × 21 columns






















<<<<<<< HEAD



 


Variables names into English and their explanation
    
=======

    Variables names into English and their explanation
      
>>>>>>> f158664ada3587c008672ed01bb08c81b8c8224b

    • Date : Date
      • 

    • HospWithSymptoms : Currently hospitalized patients with symptoms
      • 

    • IC : Intensive care
      • 

    • HospTotal: Total number of currently hospitalized patients
      • 

    • AtHome : Currently at home confinement
      • 

    • CurrentlyPositive : Total amount of current positive cases (Hospitalised patients + Home confinement)
      • 

    • NewPositives : New amount of positive cases (Actual total amount of current positive cases - total amount of current positive cases of the previous day)
      • 

    • Recovered : Recovered
      • 

    • Deaths : Deaths
      • 

    • TotalCases : Total amount of positive cases
      • 

    • NoOfTests : Tests performed
      • 

    













<<<<<<< HEAD



 


(double click and click on legend to select one or multiple regions in the graph)

=======

(double click and click on legend to select one or multiple regions in the graph)

>>>>>>> f158664ada3587c008672ed01bb08c81b8c8224b











In [69]:



    


fig = px.line(df2, x=df2.index, y="NewPositives", color="Region", hover_name="Region",
        render_mode="svg", log_y=False)
fig.update_layout(title="Daily new cases, absolute numbers")
fig.show()



    















    








        
        
            

            
        



















In [70]:



    


df2['MovAv7'] = df2['NewPositives'].rolling(window=7).mean()

fig = px.line(df2[df2.index>'2020-3-1'], x=df2.index[df2.index>'2020-3-1'], y="MovAv7", color="Region", hover_name="Region",
        render_mode="svg", log_y=False)
fig.update_layout(title="1-week rolling average of daily new cases")
fig.show()



    















    








        
        
            

            
        



















In [71]:



    


df2['NewPos_pc'] = df2['NewPositives']/df2['Pop']*1000_000

df2['NewPos_pc'] = df2['NewPos_pc'].rolling(window=7).mean()

fig = px.line(df2[df2.index>'2020-3-1'], x=df2.index[df2.index>'2020-3-1'], y="NewPos_pc", color="Region", 
              hover_name="Region", log_y=False)
fig.update_layout(title="1-week rolling average of daily new cases, per million")
fig.show()



    















    








        
        
            

            
        



















In [72]:



    


df2['IC_pc'] = df2['IC']/df2['Pop']*1000_000

fig = px.line(df2, x="Date", y="IC_pc", color="Region", hover_name="Region",
        render_mode="svg", log_y=False)
fig.update_layout(title="Current intensive care patients, per million")
fig.show()



    















    








        
        
            

            
        



















In [73]:



    


df2['Hosp_pc'] = df2['HospTotal']/df2['Pop']*1000000

fig = px.line(df2, x="Date", y="Hosp_pc", color="Region", hover_name="Region",
        render_mode="svg", log_y=False)
fig.update_layout(title="Current hospitalized, per million")
fig.show()



    















    








        
        
            

            
        



















In [75]:



    


df3 = df2.copy()

df3['NewDeaths'] = df3['Deaths'] - df3.groupby(['Region'])['Deaths'].transform('shift')

fig = px.bar(df3, x=df3['Date'], y="NewDeaths", color="Region", hover_name="Date")
fig.update_layout(title="Daily number of new deaths, absolute numbers")
fig.show()



    















    








        
        
            

            
        



















In [76]:



    


df2['NewNoOfTests'] = df2['NoOfTests'] - df2.groupby(['Region'])['NoOfTests'].transform('shift')
df2.head()

df2['New_per_test'] = df2['NewPositives']/df2['NewNoOfTests']*100

fig = px.line(df2[df2['Region'].isin(['Lombardia','Veneto','Emilia-Romagna','Piemonte','Liguria'])], 
              x=df2[df2['Region'].isin(['Lombardia','Veneto','Emilia-Romagna','Piemonte','Liguria'])].index, y="New_per_test", color="Region", hover_name="Region",
        render_mode="svg", log_y=True, line_shape='spline')
fig.update_layout(title="New positive cases in daily tests in Northern regions, %")
fig.show()



    















    








        
        
            

            
        



















In [77]:



    


df2['Deaths_per_mio'] = (df2['Deaths']/df2['Pop'])*1000_000
fig = px.line(df2, x="Date", y="Deaths_per_mio", color="Region", 
              hover_name="Region", render_mode="svg", line_shape='spline')
fig.update_layout(title="Cumulative number of deaths, per million")
fig.show()



    















    








        
        
            

            
        



















In [78]:



    


df2['Change_per_mio'] = df2['VariationOfPositives']/df2['Pop']*1000_000
df2['Change_per_mio'] = df2['Change_per_mio'].rolling(window=7).mean()


# [df2['Region'].isin(['Lombardia','Veneto','Emilia-Romagna','Piemonte','Liguria'])]
fig = px.line(df2[(df2.index>'2020-3-1') & (df2['Region']!="""Valle d'Aosta""")], x='Date', y="Change_per_mio", color="Region", hover_name="Date")
fig.update_layout(title="1-week rolling average of daily change in positive cases, per million (excl. Valle d'Aosta)")
fig.show()



    















    








        
        
            

            
        




















<<<<<<< HEAD



 


Italy as a whole
Data from all regions aggregated

=======

Italy as a whole
Data from all regions aggregated


>>>>>>> f158664ada3587c008672ed01bb08c81b8c8224b











In [80]:



    


df2 = df
df_sum = df2.drop(['Lat','Long'], axis=1).groupby(df.Date).sum().reset_index()

df_sum2 = pd.melt(df_sum, id_vars=['Date'], value_vars=['NewPositives','IC','HospTotal'])

fig = px.line(df_sum2, x="Date", y="value", color='variable', hover_name="value", render_mode="svg", log_y=True, 
              line_shape='spline')
fig.update_layout(title="Number of daily new positive cases, current IC patients and total hospitalized")
fig.show()



    















    








        
        
            

            
        



















In [ ]: